MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning
Rapid advancements in deep learning have led to many recent breakthroughs. While deep learning models achieve superior performance, often statistically better than humans, their adoption into safety-critical settings, such as healthcare or self-driving cars is hindered by their inability to provide safety guarantees or to expose the inner workings of the model in a human understandable form. We present Mo\"ET, a novel model based on Mixture of Experts, consisting of decision tree experts and a generalized linear model gating function. Thanks to such gating function the model is more expressive than the standard decision tree. To support non-differentiable decision trees as experts, we formulate a novel training procedure. In addition, we introduce a hard thresholding version, Mo\"ETH, in which predictions are made solely by a single expert chosen via the gating function. Thanks to that property, Mo\"ETH allows each prediction to be easily decomposed into a set of logical rules in a form which can be easily verified. While Mo\"ET is a general use model, we illustrate its power in the reinforcement learning setting. By training Mo\"ET models using an imitation learning procedure on deep RL agents we outperform the previous state-of-the-art technique based on decision trees while preserving the verifiability of the models. Moreover, we show that Mo\"ET can also be used in real-world supervised problems on which it outperforms other verifiable machine learning models.
Code (2)
Tasks
Game of GoImitation LearningMixture-of-ExpertsOpenAI Gymreinforcement-learningReinforcement LearningReinforcement Learning (RL)Self-Driving CarsSimilar Papers 제목 키워드 기반
MoET: Interpretable and Verifiable Reinforcement Learning via Mixture of Expert Trees
Deep Reinforcement Learning (DRL) has led to many recent breakthroughs on complex control tasks, such as defeating the best human player in the game of Go. However, decisions made by the DRL agent are not explainable, hi…
Deep Reinforcement LearningGame of GoImitation LearningMixture-of-Experts+3MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation
We present Multiple Scenario Verifiable Reinforcement Learning via Policy Extraction (MSVIPER), a new method for policy distillation to decision trees for improved robot navigation. MSVIPER learns an "expert" policy usin…
Imitation Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for post-training large language models (LLMs), achieving state-of-the-art performance on tasks with structured, verifiabl…
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs
Composing independently trained LoRA adapters into a single large language model is useful for multi-domain adaptation, especially when the original training data cannot be shared. A common approach is to use MoE-style r…
Reinforcement LearningDomain AdaptationDropout Regularization in Hierarchical Mixture of Experts
Dropout is a very effective method in preventing overfitting and has become the go-to regularizer for multi-layer neural networks in recent years. Hierarchical mixture of experts is a hierarchically gated model that defi…
Mixture-of-Experts